
We're building the future of AI security. Join a team of researchers and engineers solving problems in the industry.
We solve technical problems with methodology. Work directly on security challenges.
Small team structure. Direct contribution to product direction.
We maintain high engineering standards. Solutions protect enterprise infrastructure.
Process to determine technical and cultural fit.
Introduction call
Skills assessment
Deep dive session
Alignment fit
Onboarding
We review applications carefully. Response times may vary based on volume. All applicants receive a response.
Based in Istanbul, Turkey. Remote options available.
Research LLM vulnerabilities, prompt injection attacks, and adversarial testing methodologies.
Design security infrastructure for real-time threat detection.
Integrate security practices into product lifecycle.
Support research on LLM security vulnerabilities.
Build security tools and infrastructure.
Apply security engineering practices.
Red-team physics capabilities to prevent safety failures in industrial & scientific AI.
Red-team medical LLMs to prevent misinformation and harmful advice.
Red-team legal AI to prevent fraud enablement and illegal advice.
Red-team models to prevent dual-use checks failure (e.g., explosives, toxins).
Red-team AI to prevent biosecurity risks and pathogen design information.
For roles not listed above, contact us directly.